Downloads · 30 days
5
11% of all-time downloads
eewer/Qwen3-4B-Thinking-Preservation-terminus2-sft
Qwen3-4B-Thinking-Preservation-terminus2-sft is a text generation model from eewer. Use it when you need the model to write or continue text. It is set up for transformers. The card lists the license as apache-2.0.
eewer/Qwen3-4B-Thinking-Preservation supervised-fine-tuned for terminal-agent use in the terminus-2 format (native JSON-in-text actions; thinking preserved across multi-turn history). This is the final checkpoint of t…
Downloads · 30 days
5
11% of all-time downloads
All-time downloads
46
Public
Parameters
4B
8.8 GB on disk
Likes
0
Public
Click a slice to open those files.
.safetensors8.8 GB · 100%
From the Hugging Face model README
eewer/Qwen3-4B-Thinking-Preservation supervised-fine-tuned for terminal-agent use in the terminus-2 format (native JSON-in-text actions; thinking preserved across multi-turn history). This is the final checkpoint of the default run (globalstep 2790; ~1 epoch over the shuffled skill-based-medium terminus-2 SFT mix; AdamW, constant LR 5e-6 after a short warmup).
It is the best checkpoint by our reliable terminal-bench eval (terminus-2 harness, 6 informative live tasks, n=15 trials/task, temp 0.6 / top_p 0.95, 8192 out tokens, 40 turns):
| checkpoint | 6-task pass rate |
|---|---|
| this (default-final, s2790) | 45.6% |
| default-s999 / s1499 / s1999 | 41.1% / 40.0% / 37.0% |
| SWA merges (full-tail / last-6) | 38.9% / 37.8% |
| diverse run (best / latest) | 35.6% / 26.6% |
The raw final checkpoint beats every individual checkpoint and both stochastic-weight- averaging (SWA) merges — checkpoint merging gave no gain for this constant-LR run. Use it as a drop-in base for downstream training/eval.